model: add Clover support (#31306)
* model : add AR-only Clover MoE support Add GGUF conversion, model loading, and causal hybrid attention for Clover, reusing shared attention, recurrent-state, MoE, and LoRA helpers. * Update tests/test-llama-archs.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * convert : filter Clover tensors using filter_tensors * clover : use the standard ssm_a tensor name --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
This commit is contained in:
1 parent
1b6935b227
commit
e4b6c8ca6a
11 files changed
+560
-6
No files matched your search
@@ -2556,6 +2556,7 @@ uint32_t llama_context::graph_max_nodes(uint32_t n_tokens) const {
|
||||
model.arch == LLM_ARCH_QWEN35 ||
|
||||
model.arch == LLM_ARCH_QWEN35MOE ||
|
||||
model.arch == LLM_ARCH_CLEF ||
|
||||
model.arch == LLM_ARCH_CLOVER_MOE ||
|
||||
model.arch == LLM_ARCH_QWEN4EXP ||
|
||||
model.arch == LLM_ARCH_DEEPSEEK4 ||
|
||||
model.arch == LLM_ARCH_DEEPSEEK41 ||
|
||||
|
||||
Reference in new issue
Block a user